Related papers: TBT-Former: Learning Temporal Boundary Distributio…
Transformers are widely used in computer vision areas and have achieved remarkable success. Most state-of-the-art approaches split images into regular grids and represent each grid region with a vision token. However, fixed token…
Time series data is a key element of big data analytics, commonly found in domains such as finance, healthcare, climate forecasting, and transportation. In large scale real world settings, such data is often high dimensional and…
Falls are a major cause of injuries and deaths among older adults worldwide. Accurate fall detection can help reduce potential injuries and additional health complications. Different types of video modalities can be used in a home setting…
Video action recognition has made significant strides, but challenges remain in effectively using both spatial and temporal information. While existing methods often focus on either spatial features (e.g., object appearance) or temporal…
Deep learning models have enjoyed great success for image related computer vision tasks like image classification and object detection. For video related tasks like human action recognition, however, the advancements are not as significant…
Temporal action segmentation (TAS) in videos aims at densely identifying video frames in minutes-long videos with multiple action classes. As a long-range video understanding task, researchers have developed an extended collection of…
The identification of hazardous driving behaviors from in-cabin video streams is essential for enhancing road safety and supporting the detection of traffic violations and unsafe driver actions. However, current temporal action localization…
Temporal moment localization aims to retrieve the best video segment matching a moment specified by a query. The existing methods generate the visual and semantic embeddings independently and fuse them without full consideration of the…
Point-level supervised temporal action localization (PTAL) aims at recognizing and localizing actions in untrimmed videos where only a single point (frame) within every action instance is annotated in training data. Without temporal…
Generating high-quality videos from complex temporal descriptions that contain multiple sequential actions is a key unsolved problem. Existing methods are constrained by an inherent trade-off: using multiple short prompts fed sequentially…
This study proposes an anomaly detection method based on the Transformer architecture with integrated multiscale feature perception, aiming to address the limitations of temporal modeling and scale-aware feature representation in cloud…
Dynamic graph learning plays a pivotal role in modeling evolving relationships over time, especially for temporal link prediction tasks in domains such as traffic systems, social networks, and recommendation platforms. While…
We present TubeFormer-DeepLab, the first attempt to tackle multiple core video segmentation tasks in a unified manner. Different video segmentation tasks (e.g., video semantic/instance/panoptic segmentation) are usually considered as…
Learning representations that accurately capture long-range dependencies in sequential inputs -- including text, audio, and genomic data -- is a key problem in deep learning. Feed-forward convolutional models capture only feature…
The temporal segmentation of events is an essential task and a precursor for the automatic recognition of human actions in the video. Several attempts have been made to capture frame-level salient aspects through attention but they lack the…
Action segmentation as a milestone towards building automatic systems to understand untrimmed videos has received considerable attention in the recent years. It is typically being modeled as a sequence labeling problem but contains…
This thesis focuses on video understanding for human action and interaction recognition. We start by identifying the main challenges related to action recognition from videos and review how they have been addressed by current methods. Based…
Learning discriminative spatiotemporal representation is the key problem of video understanding. Recently, Vision Transformers (ViTs) have shown their power in learning long-term video dependency with self-attention. Unfortunately, they…
Effective spatiotemporal feature representation is crucial to the video-based action recognition task. Focusing on discriminate spatiotemporal feature learning, we propose Information Fused Temporal Transformation Network (IF-TTN) for…
Human action or activity recognition in videos is a fundamental task in computer vision with applications in surveillance and monitoring, self-driving cars, sports analytics, human-robot interaction and many more. Traditional supervised…